publications

2026

1. arXiv

   

   ReactMotion: Generating Reactive Listener Motions from Speaker Utterance

   Cheng Luo, Bizhu Wu, Bing Li, and 5 more authors

   arXiv preprint arXiv:2603.15083, 2026

   Bib HTML PDF Code

   @article{luo2026reactmotion,
     title = {ReactMotion: Generating Reactive Listener Motions from Speaker Utterance},
     author = {Luo, Cheng and Wu, Bizhu and Li, Bing and Ren, Jianfeng and Bai, Ruibin and Qu, Rong and Shen, Linlin and Ghanem, Bernard},
     journal = {arXiv preprint arXiv:2603.15083},
     year = {2026},
   }

2025

1. NeurIPS

   

   OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

   Cheng Luo, Jianghui Wang, Bing Li, and 2 more authors

   In Annual Conference on Neural Information Processing Systems, 2025

   Bib HTML PDF Code

   @inproceedings{luo2025omniresponseonlinemultimodalconversational,
     title = {OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions},
     author = {Luo, Cheng and Wang, Jianghui and Li, Bing and Song, Siyang and Ghanem, Bernard},
     booktitle = {Annual Conference on Neural Information Processing Systems},
     year = {2025},
   }

2. ACM MM

   

   ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model

   Cheng Luo, Siyang Song, Siyuan Yan, and 2 more authors

   In Proceedings of the ACM International Conference on Multimedia, 2025

   Bib HTML Code

   @inproceedings{luo2025reactidff,
     title = {ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model},
     author = {Luo, Cheng and Song, Siyang and Yan, Siyuan and Yu, Zhen and Ge, Zongyuan},
     booktitle = {Proceedings of the ACM International Conference on Multimedia},
     year = {2025},
   }

3. WACV

   

   Towards Robust Training via Gradient-Diversified Backpropagation

   Xilin He, Cheng Luo, Qinliang Lin, and 4 more authors

   In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

   Bib PDF

   @inproceedings{he2025towards,
     title = {Towards Robust Training via Gradient-Diversified Backpropagation},
     author = {He, Xilin and Luo, Cheng and Lin, Qinliang and Xie, Weicheng and Khan, Muhammad Haris and Song, Siyang and Shen, Linlin},
     booktitle = {2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     pages = {7847--7856},
     year = {2025},
   }

4. ICCV

   

   SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data

   Xilin He^*, Cheng Luo^*, Xiaole Xian, and 8 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

   Bib PDF

   @inproceedings{he2024synfer,
     title = {SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data},
     author = {He, Xilin and Luo, Cheng and Xian, Xiaole and Li, Bing and Song, Siyang and Khan, Muhammad Haris and Xie, Weicheng and Shen, Linlin and Ge, Zongyuan and Ghanem, Bernard and Yue, Xiangyu},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     year = {2025},
   }

5. PR

   

   SymGraphAU: Prior knowledge based symbolic graph for action unit recognition

   Weicheng Xie, Fan Yang, Junliang Zhang, and 4 more authors

   Pattern Recognition, 2025

   Bib PDF

   @article{xie2025symgraphau,
     title = {SymGraphAU: Prior knowledge based symbolic graph for action unit recognition},
     author = {Xie, Weicheng and Yang, Fan and Zhang, Junliang and Song, Siyang and Shen, Linlin and Yu, Zitong and Luo, Cheng},
     journal = {Pattern Recognition},
     pages = {111640},
     year = {2025},
   }

6. ACM MM

   

   REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge

   Siyang Song, Micol Spitale, Xiangyu Kong, and 8 more authors

   In Proceedings of the ACM International Conference on Multimedia, 2025

   Bib PDF Code

   @inproceedings{song2025react,
     title = {REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge},
     author = {Song, Siyang and Spitale, Micol and Kong, Xiangyu and Zhu, Hengde and Luo, Cheng and Palmero, Cristina and Barquero, German and Escalera, Sergio and Valstar, Michel and Daoudi, Mohamed and others},
     booktitle = {Proceedings of the ACM International Conference on Multimedia},
     year = {2025},
   }

2024

1. TVCG

   

   ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions

   Cheng Luo, Siyang Song, Weicheng Xie, and 4 more authors

   IEEE Transactions on Visualization and Computer Graphics, 2024

   Bib Code

   @article{luo2024reactface,
     title = {ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions},
     author = {Luo, Cheng and Song, Siyang and Xie, Weicheng and Spitale, Micol and Ge, Zongyuan and Shen, Linlin and Gunes, Hatice},
     journal = {IEEE Transactions on Visualization and Computer Graphics},
     year = {2024},
   }

2. AAAI

   

   Boosting adversarial transferability across model genus by deformation-constrained warping

   Qinliang Lin^*, Cheng Luo^*, Zenghao Niu, and 5 more authors

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2024

   Bib PDF Code

   @inproceedings{lin2024boosting,
     title = {Boosting adversarial transferability across model genus by deformation-constrained warping},
     author = {Lin, Qinliang and Luo, Cheng and Niu, Zenghao and He, Xilin and Xie, Weicheng and Hou, Yuanbo and Shen, Linlin and Song, Siyang},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {38},
     number = {4},
     pages = {3459--3467},
     year = {2024},
   }

3. CVPR

   

   Multi-scale dynamic and hierarchical relationship modeling for facial action units recognition

   Zihan Wang, Siyang Song, Cheng Luo, and 3 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

   Bib PDF Code

   @inproceedings{wang2024multi,
     title = {Multi-scale dynamic and hierarchical relationship modeling for facial action units recognition},
     author = {Wang, Zihan and Song, Siyang and Luo, Cheng and Deng, Songhe and Xie, Weicheng and Shen, Linlin},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {1270--1280},
     year = {2024},
   }

4. NeurIPS

   

   Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

   Xilin He, Jingyu Hu, Qinliang Lin, and 5 more authors

   In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

   Bib PDF Code

   @inproceedings{hetowards,
     title = {Towards Combating Frequency Simplicity-biased Learning for Domain Generalization},
     author = {He, Xilin and Hu, Jingyu and Lin, Qinliang and Luo, Cheng and Xie, Weicheng and Song, Siyang and Khan, Muhammad Haris and Shen, Linlin},
     booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
     year = {2024},
   }

5. FG

   

   React 2024: the second multiple appropriate facial reaction generation challenge

   Siyang Song, Micol Spitale, Cheng Luo, and 8 more authors

   In 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), 2024

   Bib PDF Code

   @inproceedings{song2024react,
     title = {React 2024: the second multiple appropriate facial reaction generation challenge},
     author = {Song, Siyang and Spitale, Micol and Luo, Cheng and Palmero, Cristina and Barquero, German and Zhu, Hengde and Escalera, Sergio and Valstar, Michel and Baur, Tobias and Ringeval, Fabien and others},
     booktitle = {2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)},
     pages = {1--5},
     year = {2024},
   }

2023

1. ICCV

   

   Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition

   Xilin He, Qinliang Lin, Cheng Luo, and 4 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

   Bib PDF Code

   @inproceedings{he2023shift,
     title = {Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition},
     author = {He, Xilin and Lin, Qinliang and Luo, Cheng and Xie, Weicheng and Song, Siyang and Liu, Feng and Shen, Linlin},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {1526--1535},
     year = {2023},
     url = {https://openaccess.thecvf.com/content/ICCV2023/papers/He_Shift_from_Texture-bias_to_Shape-bias_Edge_Deformation-based_Augmentation_for_Robust_ICCV_2023_paper.pdf},
   }

2. INTERSPEECH

   

   Joint prediction of audio event and annoyance rating in an urban soundscape by hierarchical graph representation learning

   Yuanbo Hou, Siyang Song, Cheng Luo, and 7 more authors

   In 24th Annual Conference of the International Speech Communication Association, 2023

   Bib PDF

   @inproceedings{hou2023joint,
     title = {Joint prediction of audio event and annoyance rating in an urban soundscape by hierarchical graph representation learning},
     author = {Hou, Yuanbo and Song, Siyang and Luo, Cheng and Mitchell, Andrew and Ren, Qiaoqiao and Xie, Weicheng and Kang, Jian and Wang, Wenwu and Botteldooren, Dick and others},
     booktitle = {24th Annual Conference of the International Speech Communication Association},
     pages = {331--335},
     year = {2023},
   }

3. ACM MM

   

   React2023: The first multiple appropriate facial reaction generation challenge

   Siyang Song, Micol Spitale, Cheng Luo, and 8 more authors

   In Proceedings of the 31st ACM International Conference on Multimedia, 2023

   Bib PDF Code

   @inproceedings{song2023react2023,
     title = {React2023: The first multiple appropriate facial reaction generation challenge},
     author = {Song, Siyang and Spitale, Micol and Luo, Cheng and Barquero, German and Palmero, Cristina and Escalera, Sergio and Valstar, Michel and Baur, Tobias and Ringeval, Fabien and Andre, Elisabeth and others},
     booktitle = {Proceedings of the 31st ACM International Conference on Multimedia},
     pages = {9620--9624},
     year = {2023},
   }

2022

1. IJCAI

   

   Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition

   Cheng Luo, Siyang Song, Weicheng Xie, and 2 more authors

   In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, 2022

   Bib PDF Code

   @inproceedings{luo2022learning,
     title = {Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition},
     author = {Luo, Cheng and Song, Siyang and Xie, Weicheng and Shen, Linlin and Gunes, Hatice},
     booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}},
     pages = {1239--1246},
     year = {2022},
   }

2. CVPR

   

   Frequency-driven imperceptible adversarial attack on semantic similarity

   Cheng Luo, Qinliang Lin, Weicheng Xie, and 3 more authors

   In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022

   Bib PDF Code

   @inproceedings{luo2022frequency,
     title = {Frequency-driven imperceptible adversarial attack on semantic similarity},
     author = {Luo, Cheng and Lin, Qinliang and Xie, Weicheng and Wu, Bizhu and Xie, Jinheng and Shen, Linlin},
     booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
     pages = {15315--15324},
     year = {2022},
   }

2021

1. ICCV

   

   Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization

   Jinheng Xie, Cheng Luo, Xiangping Zhu, and 3 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021

   Bib

   @inproceedings{xie2021online,
     title = {Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization},
     author = {Xie, Jinheng and Luo, Cheng and Zhu, Xiangping and Jin, Ziqi and Lu, Weizeng and Shen, Linlin},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     pages = {132--141},
     year = {2021},
   }